Towards in vivo ground truth susceptibility for single-orientation deep learning QSM: A multi-orientation gradient-echo MRI dataset

• Published in: NeuroImage (Orlando, Fla.) Fla.), 2022-11, Vol.261, p.119522-119522, Article 119522
• Main Authors: Shi, Yuting, Feng, Ruimin, Li, Zhenghao, Zhuang, Jie, Zhang, Yuyao, Wei, Hongjiang
• Format: Article
• Language: English
• Subjects: Algorithms; Alzheimer's disease; Benchmark; Brain; Data processing; Datasets; Deep learning; Hemorrhage; Magnetic resonance imaging; Multi-orientation GRE dataset; Multiple sclerosis; Neural networks; Quantitative susceptibility mapping; Substantia grisea; Susceptibility
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2022.119522

Recently, deep neural networks have shown great potential for solving dipole inversion of quantitative susceptibility mapping (QSM) with improved results. However, these studies utilized their limited dataset for network training and inference, which may lead to untrustworthy conclusions. Thus, a common dataset is needed for a fair comparison between different QSM reconstruction networks. Additionally, finding an in vivo reference susceptibility map that matches acquired single-orientation phase data remains an open problem. Susceptibility tensor imaging (STI) χ33 and Calculation of Susceptibility through Multiple Orientation Sampling (COSMOS) are considered reference susceptibility candidates. However, a large number of multi-orientation GRE data for both STI and COSMOS reconstruction are now unavailable for training supervised neural networks for QSM. In this study, we reported the largest multi-orientation dataset, to the best of our knowledge in the QSM research field, with a total of 144 scans from 8 healthy subjects collected using a 3D GRE sequence from the same MR scanner. In addition, the parcellation of deep gray matter is also provided for automatically extracting susceptibility values. Five recently developed deep neural networks, i.e., xQSM, QSMnet, autoQSM, LPCNN, and MoDL-QSM were performed on this dataset. This potential data source could provide a common framework and labels to test the accuracy and robustness of deep neural networks for QSM reconstruction. This dataset has the potential to provide a benchmark of reference susceptibility for the deep learning-based QSM methods. Additionally, the trained COSMOS-labeled and χ33-labeled networks were tested on the pathological data to explore their potential applications. The data together with deep gray matter parcellation maps are now publicly available via an open repository at https://osf.io/yfms7/, and the raw multi-orientation GRE data are also available at https://osf.io/y6rc3/.